AI
5 Skills That Make Your Coding Agent Work Better
I gave a coding agent five skills and one real bug. Here's how each skill changed what the agent did, with the actual output.
Lince Mathew
browsers
A Headless Browser Without a Rendering Engine, Built for Agents
Puppeteer and Playwright run Chromium's full rendering pipeline on every page load, even though nothing is ever shown. Here is the architecture of a headless browser built without one.
AI
Your AI Assistant Forgets Everything. Memory Layers Fix That
Your agent forgets everything between sessions, and config files only hold the rules you knew to write down in advance. Here's what a memory layer actually does, and what happened when I wired mem0 into Claude Code and let it run on its own.
finance
Manage Finance Like a Codebase
As developers, we trust Git with our code, our configs, even our notes, but never our money. Here's what happened when I found a tool that treats your finances exactly like a codebase: plain text, versioned, and diffable
AI
Does your team use different AI agents? Here’s how to standardize your products.
If your team uses a mix of Cursor, Claude Code, and Copilot, things can get messy fast. In this article, we explain how to set up a system to standardize your products, keep your design system consistent, and ensure every AI agent plays by the exact same rules.
AI
Searching Billions in Seconds: How HNSW Solved the Scale Problem
Discover how HNSW solved the scale problem for Approximate Nearest Neighbor Search by creating a multi-layered graph system that can search through billions of items in milliseconds.
llm
How AI Systems Self-Correct with LangGraph?
Learn how LangGraph enables AI systems to self-correct and handle complex tasks autonomously.
pagespeed
Try These Proven Techniques for Improving Your Webpage Speed
Learn how we boosted FreeDevTools' PageSpeed Insights score to a near-perfect 95. From optimizing TTFB to implementing critical CSS, we'll cover the key strategies that transformed our site's performance.
machine learning
How Netflix Uses Matrix Factorization to Predict Your Next Favorite Movie
Discover how Matrix Factorization solves the empty star problem that once challenged Netflix. This article explores using Stochastic Gradient Descent to bridge the gap between missing data and perfect matches.
llms
Stop Paying for LLMs — Run Your Own Locally
If you’re tired of hitting limits, waiting on slow responses, or paying monthly just to use an online model, there’s a better option. With Ollama, you can run powerful LLMs directly on your own machine.
go
Fan-In and Fan-Out in Go: Parallelism Made Simple
Learn how to distribute work across multiple goroutines and merge their results back into a single stream using Go's Fan-Out and Fan-In patterns. We'll break down these powerful concurrency patterns with practical examples you can use right away.
seo
Is Your Website Fast Enough? What Google's Core Web Vitals Reveal
Want to know if your website is fast enough? Google's Core Web Vitals measure three key things: how quickly your page loads, how fast it responds to clicks, and whether it jumps around while loading. Fix these, and you'll rank better while giving users a smoother experience.